© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-65K
    4. 1006
    Prev
    Next
    INDEX
    Explanations

    markdown formatting and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ھوں
    0.38
    朊
    0.34
     thatch
    0.32
     paralysie
    0.32
    وڑا
    0.32
    餒
    0.32
    бль
    0.31
    ینګ
    0.31
     cuisses
    0.30
     chemins
    0.30
    POSITIVE LOGITS
     **
    0.42
    </div>
    0.41
    #####
    0.40
    ###
    0.40
    **
    0.40
    ####
    0.38
    >**
    0.38
    ##
    0.37
    </li>
    0.35
    		
    0.35
    Activations Density 0.080%

    No Known Activations